### What problem does this PR solve?
This PR fixes a regression where Manual pipeline + Naive (Plain Text)
PDF parsing crashed with `AttributeError: 'PlainParser' object has no
attribute 'extract_positions'` in `rag/app/manual.py`.
fixes#14411
### Type of change:
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add executor shutdown in finally clause to free resources.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This PR fixes issue #14371 where file parsing failed after upgrading
from v0.24.0 to v0.25.0, because metadata config could be a JSON Schema
object but was handled like a list and later caused `KeyError:
'properties'`.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fixes#14196
## Problem
When using DeepDOC to parse large PDFs (over 1000 pages), the parser
silently truncated processing at 300 pages due to a hardcoded default
`page_to=299` in `RAGFlowPdfParser.__images__()`. This caused:
- **Errors** on pages beyond the limit
- **Poor image quality** as the parser attempted to compensate with
missing page data
- **Inconsistent chunk splitting** between full PDF imports and partial
imports
Additionally, the codebase scattered magic numbers (`299`, `600`,
`10000`, `100000`, `100000000`, `10000000000`, `10**9`) across 22 files
as sentinel values for "parse all pages", making future maintenance
error-prone.
## Root Cause
```python
# deepdoc/parser/pdf_parser.py (before)
def __images__(self, fnm, zoomin=3, page_from=0, page_to=299, callback=None):
# Only the first 300 pages were rendered; everything beyond was silently dropped
```
While most callers in `rag/app/*.py` correctly passed `to_page=100000`,
the base class `RAGFlowPdfParser.__call__()` and `parse_into_bboxes()`
invoked `__images__` **without** forwarding `page_from`/`page_to`,
falling back to the restrictive default of 299.
## Solution
### 1. Define constants in `common/constants.py`
```python
MAXIMUM_PAGE_NUMBER = 100000 # Used by the parsing layer
MAXIMUM_TASK_PAGE_NUMBER = MAXIMUM_PAGE_NUMBER * 1000 # Used by the task/DB layer
```
### 2. Replace all hardcoded sentinel values
| Layer | Files Changed | Old Values | New Value |
|---|---|---|---|
| **Deepdoc parsers** | `pdf_parser.py`, `mineru_parser.py`,
`docling_parser.py`, `opendataloader_parser.py`, `paddleocr_parser.py`,
`docx_parser.py` | `299`, `600`, `10**9`, `100000000` |
`MAXIMUM_PAGE_NUMBER` |
| **Chunk parsers** | `naive.py`, `book.py`, `qa.py`, `one.py`,
`manual.py`, `paper.py`, `presentation.py`, `laws.py`, `resume.py`,
`email.py`, `table.py` | `100000`, `10000`, `10000000000` |
`MAXIMUM_PAGE_NUMBER` |
| **Task/DB layer** | `db_models.py`, `task_service.py`,
`document_service.py`, `file_service.py` | `100000000` |
`MAXIMUM_TASK_PAGE_NUMBER` |
### 3. Fix `parse_into_bboxes()` missing parameters
Added `from_page`/`to_page` parameters to `parse_into_bboxes()` so that
the `rag/flow/parser/parser.py` DeepDOC path no longer falls back to the
restrictive default.
## Files Changed (22)
- `common/constants.py`
- `deepdoc/parser/pdf_parser.py`
- `deepdoc/parser/mineru_parser.py`
- `deepdoc/parser/docling_parser.py`
- `deepdoc/parser/opendataloader_parser.py`
- `deepdoc/parser/paddleocr_parser.py`
- `deepdoc/parser/docx_parser.py`
- `rag/app/naive.py`
- `rag/app/book.py`
- `rag/app/qa.py`
- `rag/app/one.py`
- `rag/app/manual.py`
- `rag/app/paper.py`
- `rag/app/presentation.py`
- `rag/app/laws.py`
- `rag/app/resume.py`
- `rag/app/email.py`
- `rag/app/table.py`
- `api/db/db_models.py`
- `api/db/services/task_service.py`
- `api/db/services/document_service.py`
- `api/db/services/file_service.py`
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
---------
Signed-off-by: noob <yixiao121314@outlook.com>
## Summary
PDF files often contain a bookmark/outline tree (table of contents built
into the file by the authoring tool). RAGFlow's `pdf_parser.outlines`
already extracts these `(title, depth)` tuples via pypdf, but they are
used ephemerally during chunking (`manual` parser uses them for
hierarchy detection) and then discarded.
This PR persists the outline as `doc.meta_fields["outline"]` — a JSON
array of `{"title": str, "depth": int}` objects — so downstream features
can use the structural information.
### Why this matters
- **Complementary to `toc_extraction`** — the existing `toc_extraction`
feature uses LLM calls to generate a TOC and only works for the `naive`
parser. The raw PDF outline is free (already extracted by pypdf), works
for all parsers, and captures the author's original document structure.
- **Document navigation** — frontends can render a clickable TOC from
the outline
- **Entity extraction** — the outline provides a structural map for
identifying document sections and key topics
- **Search result context** — knowing which section a chunk belongs to
helps users evaluate relevance
### Changes
| File | Change | LOC |
|------|--------|-----|
| `rag/app/naive.py` | Attach `pdf_parser.outlines` as `__outline__` on
first chunk dict | ~7 |
| `rag/app/manual.py` | Same for the manual parser | ~5 |
| `rag/svr/task_executor.py` | Extract `__outline__`, persist via
`DocMetadataService.update_document_metadata()` | ~12 |
### Design decisions
- **Transient key pattern**: The outline is passed from parser →
task_executor via `__outline__` on the first chunk dict, then removed
before indexing. This follows the same pattern as `metadata_obj` for
LLM-generated metadata.
- **No schema changes**: Uses the existing `meta_fields` JSON column on
the document table.
- **Graceful degradation**: If a PDF has no outline (common for scanned
docs), nothing is stored. If persistence fails, it logs a warning and
continues — parsing is not interrupted.
### Backward compatibility
- **Fully backward compatible** — no existing fields, behavior, or
schemas changed
- PDFs without outlines are unaffected
- Existing `meta_fields` data is preserved (merged, not overwritten)
## Test plan
- [ ] Parse a PDF with bookmarks (e.g. any multi-chapter document),
verify `meta_fields["outline"]` is populated
- [ ] Parse a PDF without bookmarks, verify no errors and no outline key
in meta_fields
- [ ] Verify existing `meta_fields` data is preserved (not overwritten)
when outline is added
- [ ] Verify `manual` parser also persists outlines
- [ ] Verify outline JSON structure: `[{"title": "Chapter 1", "depth":
0}, ...]`
Related: #9921 (Deterministic Document Access Layer)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: yuch85 <yuch85.1@gmail.com>
Co-authored-by: Wang Qi <wangq8@outlook.com>
### What problem does this PR solve?
## Summary
Closes#6102
When using Infinity as the document store engine (GPU version), calling
`update()` on a non-existent table throws an unhandled
`InfinityException` with error code 3022 (`TABLE_NOT_EXIST`). This
causes users to see a raw "3022" error when clicking on a parsed
document.
## Root Cause
The `update()` methods in both `rag/utils/infinity_conn.py` and
`memory/utils/infinity_conn.py` call `db_instance.get_table(table_name)`
without catching `InfinityException`. In contrast, other CRUD methods
(`insert`, `delete`, `search`) all handle this exception gracefully:
| Method | Handles table-not-exist? | Behavior |
|----------|--------------------------|----------|
| `insert` | ✅ Yes | Auto-creates the table |
| `search` | ✅ Yes | Skips the table |
| `delete` | ✅ Yes | Returns 0 |
| `update` | ❌ **No** | Crashes with 3022 |
Additionally, `api/apps/document_app.py` worked around this with a
fragile string match (`"3022" in msg`) to detect the error.
## Changes
- **`rag/utils/infinity_conn.py`**: Catch `InfinityException` in
`update()`. When `TABLE_NOT_EXIST` is detected, log a warning and return
`False` — consistent with `delete()`.
- **`memory/utils/infinity_conn.py`**: Apply the same fix to its
`update()` method.
- **`api/apps/document_app.py`**: Remove the fragile `"3022"`
string-matching workaround. Table-not-exist is now handled by the `if
not ok` path with an improved error message.
### Type of change
- [x] Refactoring
---------
Signed-off-by: noob <yixiao121314@outlook.com>
## Summary
RAPTOR's recursive clustering builds a `layers` list tracking
`(start_idx, end_idx)` boundaries per level, but currently discards this
information — only the flat `chunks` list is returned. This makes it
impossible to distinguish leaf-level summaries from top-level ones.
This PR:
- Returns `(chunks, layers)` tuple from `raptor.py`'s `__call__`
- Annotates each RAPTOR summary chunk with `raptor_layer_int` (1 = first
summary level, 2 = summary-of-summaries, etc.)
- Adds `raptor_layer_int` to `infinity_mapping.json` (Elasticsearch
handles it via existing `*_int` dynamic template)
### Why this matters
Downstream features need to know which RAPTOR layer a summary belongs
to:
- **Retrieving the top-level document summary** for entity extraction,
search snippets, or document comparison
- **Filtering by abstraction level** — users may want only high-level
summaries or only leaf-level cluster summaries
- **RAPTOR recall quality** — #10951 reports summaries not being
recalled for definition queries; layer metadata enables targeted
retrieval
### Changes
| File | Change | LOC |
|------|--------|-----|
| `rag/raptor.py` | Return `(chunks, layers)` tuple | ~3 |
| `rag/svr/task_executor.py` | Build `chunk_layer` mapping, set
`raptor_layer_int` | ~12 |
| `conf/infinity_mapping.json` | Add `raptor_layer_int` integer field |
~1 |
### Backward compatibility
- **Additive only** — no existing fields or behavior changed
- Existing RAPTOR chunks continue to work (they'll have
`raptor_layer_int = 0` by default)
- New RAPTOR chunks get layer metadata automatically
## Test plan
- [ ] Parse a document with RAPTOR enabled, verify `raptor_layer_int` is
set on indexed chunks
- [ ] Verify `raptor_layer_int` values increase with abstraction level
(layer 1 < layer 2 < ...)
- [ ] Verify existing RAPTOR deletion (`delete by raptor_kwd`) still
works
- [ ] Verify Infinity backend accepts the new field
Fixes#7488
Related: #4104, #11191, #10951🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: yuch85 <yuch85.1@gmail.com>
Co-authored-by: Wang Qi <wangq8@outlook.com>
### What problem does this PR solve?
Allow search id or _id when using es as doc_engine.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: introduce minimum type check for pipeline
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Blob storage sync was downloading unsupported files first and rejecting
them later, which wasted bandwidth and made sync slower. This PR skips
unsupported extensions before download and applies `allow_images` in
blob sync. fixes#14338
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
when use azure blob as the file container, when click parse file, it
calls:
```python
partial(settings.STORAGE_IMPL.put, tenant_id=task["tenant_id"])
```
So any storage backend used there must accept tenant_id as a kwarg.
RAGFlowAzureSasBlob.put() did not, causing:
```
TypeError: ... got an unexpected keyword argument 'tenant_id'
```
Now it does, so parsing should proceed past this point.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This PR fixes the merge-phase crash reported in #14236 during GraphRAG
entity resolution.
The issue happens after candidate pair resolution completes, when
multiple merge coroutines mutate the same shared `networkx` graph
concurrently. In `_merge_graph_nodes`, the code iterates over
`graph.neighbors(node1)` and also awaits during edge/description
merging. That allows another coroutine to modify the graph adjacency
structure in between, which can trigger `RuntimeError: dictionary keys
changed during iteration` and can also lead to unsafe shared-graph
mutation.
This change keeps the PR scoped to that single issue by:
- serializing merge-time graph mutations with a dedicated merge lock
- snapshotting `graph.neighbors(node1)` with `list(...)` before
iteration
Together, these changes prevent concurrent mutation of the shared graph
during the merge phase and make the merge loop safe against live-view
invalidation.
Fixes#14236
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
### What problem does this PR solve?
Get metadata configuration from union of custom metadata and
built_in_metadata.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
OpenSource Resume is supported only with Elasticsearch.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
https://bailian.console.aliyun.com/cn-beijing?tab=api#/api/?type=model&url=2780056
### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [x] Other (please describe): add gte-rerank-v2、qwen3-rerank
Closes#9078
### What problem does this PR solve?
The `retrieval_test` endpoint in `chunk_app.py` never forwarded the
`highlight` request parameter to `retriever.retrieval()`, so the search
engine never produced highlight snippets. Additionally, the frontend
always rendered `content_with_weight` instead of preferring the
`highlight` field, and the CSS rule color `var(--accent-primary)` didn't
work because the variable stores an RGB triplet `(45,212,191)` requiring
the `rgb()` wrapper.
### Before
- Search page: displayed raw content_with_weight as a wall of plain
white text with no term highlighting, including markdown headings
rendered as literal text
- Retrieval testing page: showed `content_with_weight` in a plain `<p>`
tag, no `<em>` tags rendered, no highlight coloring
- Children chunks: when child chunks were consolidated into a parent via
`retrieval_by_children`, any highlight data from children was discarded
- TOC chunks: chunks fetched via `retrieval_by_toc` had no `highlight`
field, appearing as plain text while other chunks had highlights
**Retrieval testing**:
<img width="1449" height="1178"
alt="before-retrieval-no-highlight-cropped"
src="https://github.com/user-attachments/assets/5c6f5a5e-6c11-461a-bdb4-049d7dfb7a33"
/>
**Search**:
<img width="1378" height="711" alt="before-search-no-highlight-cropped"
src="https://github.com/user-attachments/assets/be7b5152-72ef-40da-a8fd-921e997ae7d3"
/>
### After
- Search page: displays the highlight field with search terms rendered
in teal/cyan color (`rgb(var(--accent-primary))`)
- Retrieval testing page: sends highlight: true in the request, uses
`HighLightMarkdown` component to render `<em>` tags with proper coloring
- Children chunks: highlights from child chunks are joined and preserved
on the parent
- TOC chunks: when other chunks have highlights, TOC-fetched chunks use
`content_with_weight` as a highlight fallback
**Retrieval testing**:
<img width="1410" height="1015" alt="05-retrieval-testing-results"
src="https://github.com/user-attachments/assets/f0cff8cf-0962-4320-b559-cd5037f622d2"
/>
**Search**:
<img width="1294" height="455" alt="03-search-highlight-results"
src="https://github.com/user-attachments/assets/a90e0e3e-3837-46be-8ddd-2412ff7cbc19"
/>
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Resolve#14137 .
### Problem
Graph resolution succeeds (nodes/edges merged, pagerank updated), but
the subsequent burst of Infinity write operations in `set_graph`
exhausts the connection pool with `TOO_MANY_CONNECTIONS` errors. Root
causes:
1. **Hardcoded pool size** — `infinity_conn_pool.py` hardcoded
`ConnectionPool(max_size=4)` on initial creation and `max_size=32` on
refresh. Operators cannot tune this without patching code.
2. **No retry on transient failures** — a single `TOO_MANY_CONNECTIONS`
on edge deletes or chunk inserts kills the entire resolution+community
pipeline with no retry.
### Changes
#### `common/doc_store/infinity_conn_pool.py`
- Read `ConnectionPool` `max_size` from the `INFINITY_POOL_MAX_SIZE`
environment variable (default: `4`), applied consistently to both
initial creation and refresh paths.
- Log the actual pool size on startup for easier debugging.
#### `rag/graphrag/utils.py` — `set_graph()`
- **Edge deletes**: add exponential-backoff retry (3 attempts, 1s/2s/4s
delays) so transient `TOO_MANY_CONNECTIONS` errors are retried instead
of failing the entire job. Concurrency continues to be gated by the
existing `chat_limiter`.
- **Batch inserts**: add exponential-backoff retry (3 attempts, 1s/2s/4s
delays) for the same reason.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Signed-off-by: noob <yixiao121314@outlook.com>
### What problem does this PR solve?
Feat: add button to turn off vlm parsing
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: chanx <1243304602@qq.com>
### What problem does this PR solve?
Feat: update templates && add resume template
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Addresses review feedback on #14074 (Checkpoint mechanism for
long-running workflow jobs, issue #12494).
**Changes based on @yuzhichang's review:**
1. **Renamed `checkpoint_service.py` → `task_checkpoint.py`** as
suggested.
2. **Replaced Redis with direct docEngine queries** as suggested — the
subgraph already gets persisted to the doc store by
`generate_subgraph()`, so we just query for it instead of maintaining a
separate checkpoint in Redis. This is simpler, has no extra dependency,
and uses a single source of truth.
**Changes based on CodeRabbit review:**
3. **Fixed `source_id` query format mismatch** — subgraphs are stored
with `source_id: [doc_id]` (list), but the original query used
`source_id: doc_id` (string). Now follows the same pattern as
`does_graph_contains()` in `rag/graphrag/utils.py`: filter by
`knowledge_graph_kwd` only, then match `source_id` in Python. This
avoids ambiguity across Elasticsearch / Infinity / OceanBase backends.
### Changes
| File | Change |
|---|---|
| `api/db/services/task_checkpoint.py` (new) |
`load_subgraph_from_store()` and `has_raptor_chunks()` — docEngine-based
checkpoint queries |
| `rag/graphrag/general/index.py` | `build_one()` calls
`load_subgraph_from_store()` before running LLM extraction |
| `rag/svr/task_executor.py` | RAPTOR per-doc loop calls
`has_raptor_chunks()` before processing |
| `test/unit_test/rag/graphrag/test_checkpoint_resume.py` (new) | 10
unit tests covering subgraph loading, source_id filtering, edge cases |
### How it works
- **GraphRAG:** Before running expensive LLM entity/relation extraction
for a doc, checks the doc store for an existing subgraph (saved by a
previous interrupted run). If found, loads it directly and skips LLM
calls.
- **RAPTOR:** Before processing a doc, checks if RAPTOR chunks
(`raptor_kwd="raptor"`) already exist for it. If yes, skips.
### Testing
- 10 new unit tests — all passing
- Full existing suite: 617 passed
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
## Summary
- remove eval-based parsing from retrieval rank feature scoring
- validate `tag_feas` at write time in chunk APIs and SDK routes
- add regression tests for safe parsing and malicious payload rejection
## Details
`tag_feas` is intended to be structured rank-feature data, but the
retrieval ranking path was evaluating stored values as Python
expressions. This change treats `tag_feas` strictly as data.
### What changed
- replace `eval()` in `rag/nlp/search.py` with safe parsing via
`json.loads()` and optional `ast.literal_eval()` compatibility for
legacy Python-dict strings
- strictly filter parsed values down to `dict[str, finite number]`
- reject invalid `tag_feas` payloads at write time in web chunk routes
and SDK document chunk routes
- add focused regression tests to prove executable strings are ignored
and invalid payloads are rejected
## Validation
- `python -m pytest test/unit_test/common/test_tag_feature_utils.py
test/unit_test/rag/test_rank_feature_scores.py -q`
---------
Co-authored-by: unknown <zhenglinkai@CCN.Local>
Co-authored-by: Yingfeng Zhang <yingfeng.zhang@gmail.com>
### What problem does this PR solve?
Fixes#14051.
The chat UI already sends an `internet` flag with each request, but the
backend previously triggered Tavily web retrieval whenever
`prompt_config.tavily_api_key` was configured. As a result, web search
could still run even when the internet toggle was off.
This PR makes web search an explicit opt-in at request time:
- `tavily_api_key` only indicates that web search is available
- Tavily retrieval runs only when `internet` is explicitly enabled
- the same behavior now applies to both the normal retrieval path and
the deep-research / reasoning path
This also fixes the no-KB fallback case so chats without KBs fall back
to normal solo chat when `internet` is off.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This fixes rerank overflow where retrieval could send more documents
than allowed (for example 66 when `page_size=6`), causing provider 400
errors and bypassing the user’s `top_k` intent in rerank-enabled paths.
this pr fixes#14081
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Visit
`http://127.0.0.1:9381/?__debugger__=yes&cmd=resource&f=debugger.js`
will expose the flask code:
```
docReady(() => {
if (!EVALEX_TRUSTED) {
initPinBox();
}
// if we are in console mode, show the console.
if (CONSOLE_MODE && EVALEX) {
createInteractiveConsole();
}
const frames = document.querySelectorAll("div.traceback div.frame");
if (EVALEX) {
addConsoleIconToFrames(frames);
}
addEventListenersToElements(document.querySelectorAll("div.detail"), "click", () =>
document.querySelector("div.traceback").scrollIntoView(false)
);
addToggleFrameTraceback(frames);
addToggleTraceTypesOnClick(document.querySelectorAll("h2.traceback"));
addInfoPrompt(document.querySelectorAll("span.nojavascript"));
wrapPlainTraceback();
});
function addToggleFrameTraceback(frames) {
frames.forEach((frame) => {
frame.addEventListener("click", () => {
frame.getElementsByTagName("pre")[0].parentElement.classList.toggle("expanded");
});
})
}
```
### Type of change
- [x] Other (please describe): Fix security risk
### What problem does this PR solve?
Feat: pipeline support ONE chunking method
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
### What problem does this PR solve?
Fix: support vlm fall back in pipeline for img/table parsing
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
GraphRAG _async_chat.
### Type of change
- [x] Refactoring
- [x] Performance Improvement
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Refactor**
* Unified chat calls to an async invocation across extractors, improving
timeout handling and ensuring task IDs propagate reliably.
* **Tests**
* Added and expanded unit tests and mocks to cover extractor behavior,
timeout scenarios, and safe test-package imports, reducing regression
risk.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Fixes#13823
## Problem
When querying with words like `cat`, RAGFlow's query expansion system
looks up synonyms via WordNet, which can return terms containing single
quotes (e.g., `cat-o'-nine-tails`). When using Infinity as the document
store, these unescaped single quotes in the query string cause a
`TokenError` because Infinity's lexer treats `'` as a string delimiter.
```
TokenError: Error tokenizing ' OR "big cat" OR "computerized tomography")^0.7)': Missing ' from 1:531
```
## Solution
Strip single quotes from synonym terms before they are inserted into
query expressions, consistent with how single quotes are already
stripped from the input query text (line 51 of `query.py`):
- **`common/query_base.py`**: In `sub_special_char()`, strip `'` before
escaping other special characters. This fixes the Chinese text
processing path and the `paragraph()` method.
- **`rag/nlp/query.py`**: In the English text path, strip `'` from
tokenized synonym terms.
- **`memory/services/query.py`**: Same fix for the memory query English
text path.
## Testing
The fix can be verified by:
1. Using Infinity as the document store (`DOC_ENGINE=infinity`)
2. Creating a dataset and running a retrieval test with the keyword
`cat`
3. Confirming no `TokenError` is raised and results are returned
normally
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Bug Fixes**
* Enhanced special character handling in query processing and synonym
expansion by properly sanitizing single quotes before text processing.
* Simplified OCR detection output by removing timing metadata while
preserving core detection accuracy.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: ximi <octo-patch@github.com>
fix: support dense_vector from ES fields response (ES 9.x compatibility)
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Configuration Chore (non-breaking change which updates
configuration)
## Summary by CodeRabbit
* **Bug Fixes**
* More accurate handling and unwrapping of dense-vector fields so
returned values have correct shapes.
* Field selection reliably limits returned data and falls back to
alternate result locations when needed.
* Use of consistent result IDs and tolerant handling when score values
are missing.
* **Chores / Configuration**
* Increased build memory and adjusted build-time flags for the frontend
build.
* Simplified runtime model/GPU checks and removed an automated runtime
GPU-install attempt.
* **Build Fixes**
* `web/vite.config.ts`: make `build.minify` and `build.sourcemap`
respect `VITE_MINIFY` and `VITE_BUILD_SOURCEMAP` env vars from
Dockerfile instead of hardcoding `terser` and `true`.
* **Environment**
* Allow stack version override and default the runtime image tag to
"latest".
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Bug Fixes**
* Correct unwrapping of dense-vector fields and reliable field selection
with fallback locations.
* Consistent use of hit-level IDs and tolerant handling when score
values are missing.
* **Chores / Configuration**
* Increased frontend build memory and added build-time minify/sourcemap
flags; build minification and sourcemap now configurable.
* Removed runtime GPU detection for model initialization; force CPU
initialization.
* **Environment**
* Allow stack version override and default runtime image tag to
"latest".
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
### What problem does this PR solve?
Feat: support doc for pipeline parser in word
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added support for processing legacy Word `.doc` file formats,
extending document compatibility.
* **Bug Fixes**
* Enhanced error handling during document parsing to improve reliability
and prevent processing failures.
### What problem does this PR solve?
Feat: enable sync deleted files for connector
1. first comes with github
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added "sync deleted files" feature for data sources, enabling
automatic removal of files deleted from the source system.
* Added multilingual support for the new sync deleted files setting
across multiple languages.
* **UI Improvements**
* Improved checkbox form field rendering and layout.
* Enhanced full-width display for authentication token input fields.
### What problem does this PR solve?
Implements automatic adjustment of knowledge base chunk recall weights
based on user feedback (upvotes/downvotes). When users upvote or
downvote a response, the system locates the corresponding knowledge
snippets and adjusts their recall weight to improve future retrieval
quality.
**Closes #12670**
**How it works:**
1. User upvotes/downvotes a response via `POST /thumbup`
2. System extracts chunk IDs from the conversation reference
3. For each referenced chunk:
- Reads current `pagerank_fea` value from document store
- Increments (+1) for upvote or decrements (-1) for downvote
- Clamps weight to [0, 100] range
- Updates chunk in ES/Infinity/OceanBase
4. Future retrievals score these chunks higher/lower based on
accumulated feedback
**Files changed:**
- `api/db/services/chunk_feedback_service.py` - New service for updating
chunk pagerank weights
- `api/apps/conversation_app.py` - Integrated feedback service into
thumbup endpoint
- `test/testcases/test_web_api/test_chunk_feedback/` - Unit tests
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Chat message feedback now updates per-chunk relevance weights
(feature-flag gated), with configurable weighting and atomic updates
across storage backends.
* **Bug Fixes**
* Stricter validation for message feedback inputs and more robust
handling of feedback transitions.
* **Tests**
* Expanded test coverage for chunk-feedback behavior, weighting
strategies, storage backends, and thumb-flip scenarios.
* **Chores**
* CI workflow extended to run the new chunk-feedback web API tests.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: mkdev11 <YOUR_GITHUB_ID+MkDev11@users.noreply.github.com>
Co-authored-by: mkdev11 <MkDev11@users.noreply.github.com>
## Summary
- Add optional `region` parameter to `Minio()` client constructor in
`rag/utils/minio_conn.py`
- Reads from `MINIO.region` in settings, defaults to `None` when not
configured
- Required by some S3-compatible storage services (e.g., AWS S3, Tencent
COS) for proper bucket access
## Motivation
When using RAGFlow with S3-compatible storage that requires a region
(such as AWS S3 or Tencent Cloud COS), the MinIO client fails to access
buckets because the `region` parameter is not passed through.
The `Minio()` Python client already supports the `region` parameter
natively — this PR simply wires it up from the RAGFlow configuration.
## Changes
- `rag/utils/minio_conn.py`: Pass `region=settings.MINIO.get("region",
None) or None` to `Minio()` constructor
## Backward Compatibility
- No breaking changes. When `region` is not configured, it defaults to
`None`, preserving the existing behavior exactly.
## Test Plan
- [ ] Verified with MinIO (no region set) — works as before
- [x] Verified with S3-compatible storage requiring region — bucket
access succeeds
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Bug Fixes**
* Enhanced MinIO client initialization with regional configuration
support for improved compatibility with region-specific deployments.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Co-authored-by: Jarry Wang <code-better-life@users.noreply.github.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## Summary
- Fix `a image` → `an image` in README and log message
- Fix `colomn` → `column` in table structure recognizer comment
- Fix `formated` → `formatted` in confluence connector docstring
- Fix `tabel of content` → `table of contents` in TOC prompt
## Test plan
- [ ] Documentation and comment changes, no functional impact
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: yuj <yuj@ztjzsoft.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Add validation logic for parser_config.
Refactor the processing flow. Before change, validation logics and
update logics are mixed up - some validation logis executes followed by
some update logic executes and then another such
"validation-and-then-update" which is not good. After change, all
validation logic executes firstly. Update logic will be executed after
ALL validation logic executed.
Validation logic for parameters (that come from front end) will be
checked using Pydantic. For validation logic that depends on data from
DB, they will be in separate methods.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
### What problem does this PR solve?
fix#13944 where OpenAI-compatible custom endpoints failed verification
when model names contained `gpt-5` becauser of incorrect name-based
handling in the Base/backend=`base` path.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
The MySQL and PostgreSQL sync classes in `sync_data_source.py` were not
passing `id_column`, `timestamp_column`, and `metadata_columns` to
`RDBMSConnector`,
making incremental sync and document update impossible even when
configured.
- Without `id_column`: updated records generate new documents instead of
overwriting existing ones (doc ID is derived from content hash, so any
change produces a new ID).
- Without `timestamp_column`: `poll_source` always falls back to full
sync,
ignoring the configured time range.
- The three fields existed in the frontend default values but had no
form
inputs, so users had no way to fill them in.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
### Changes
- **Backend** (`rag/svr/sync_data_source.py`): pass `id_column`,
`timestamp_column`, and `metadata_columns` from `self.conf` to
`RDBMSConnector` for both `MySQL` and `PostgreSQL` sync classes.
- **Frontend**
(`web/src/pages/user-setting/data-source/constant/index.tsx`):
add `ID Column`, `Timestamp Column`, and `Metadata Columns` form fields
to MySQL and PostgreSQL data source configuration UI with tooltips.
Signed-off-by: lixintao <lixintao@uniontech.com>
Co-authored-by: lixintao <lixintao@uniontech.com>
